What are the hardware requirements for PiVoT 10.7B Mistral V0.2?

PiVoT 10.7B Mistral V0.2 requires approximately 21.4 GB of VRAM and supports a context window of 32K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed PiVoT 10.7B Mistral V0.2 and how large is it?

PiVoT 10.7B Mistral V0.2 is developed by maywell, a model with 10.7b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does PiVoT 10.7B Mistral V0.2 perform on standard benchmarks?

PiVoT 10.7B Mistral V0.2 has the following published scores: MMLU 59.86. Compare against reference models on this page or on the LLM Explorer leaderboards.

PiVoT 10.7B Mistral V0.2 by maywell — VRAM 21.4GB, 32K context

Name: PiVoT 10.7B Mistral V0.2
Author: maywell

PiVoT 10.7B Mistral V0.2 is an open-source language model by maywell. Features: 10.7b LLM, VRAM: 21.4GB, Context: 32K, License: cc-by-sa-4.0, LLM Explorer Score: 0.12, Arc: 63.3, HellaSwag: 81.7, MMLU: 59.9, GSM8K: 42.4.

Conversational Deploy:azure En Endpoints compatible Ko Mistral Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/maywell/PiVoT-10.7B-Mistral-v0.2

PiVoT 10.7B Mistral V0.2 Parameters and Internals

Model Type

text-generation

Additional Notes

PivoT is a finetuned model based on a merge of Mistral 0.2.

Supported Languages

en (English), ko (Korean)

Training Details

Methodology:

SFT + DPO

LLM Name	PiVoT 10.7B Mistral V0.2
Repository 🤗	https://huggingface.co/maywell/PiVoT-10.7B-Mistral-v0.2
Model Size	10.7b
Required VRAM	21.4 GB
Updated	2026-07-19
Maintainer	maywell
Model Type	mistral
Model Files	4.9 GB: 1-of-5 5.0 GB: 2-of-5 4.9 GB: 3-of-5 4.9 GB: 4-of-5 1.7 GB: 5-of-5
Supported Languages	en ko
Model Architecture	MistralForCausalLM
License	cc-by-sa-4.0
Context Length	32768
Model Max Length	32768
Transformers Version	4.36.0.dev0
Tokenizer Class	LlamaTokenizer
Padding Token	</s>
Vocabulary Size	32000
Torch Data Type	bfloat16

Rank the PiVoT 10.7B Mistral V0.2 capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

Quantized Models of the PiVoT 10.7B Mistral V0.2

Model	Likes	Downloads	VRAM
PiVoT 10.7B Mistral V0.2 GGUF	5	163	4 GB
PiVoT 10.7B Mistral V0.2 GPTQ	3	11	6 GB
PiVoT 10.7B Mistral V0.2 AWQ	2	3	6 GB

Best Alternatives to PiVoT 10.7B Mistral V0.2

Best Alternatives	Context / RAM	Downloads	Likes
Barely Regal 10.7B	32K / 21.5 GB	19	0
Quintellect 10.7B	32K / 21.4 GB	22	3
Chikuma 10.7B	32K / 21.4 GB	131	5
Longcat 10.7B	32K / 21.5 GB	8	3
Multi Verse Model 10.7B	32K / 21.5 GB	2	1
PrimaSumika 10.7B 128K	32K / 21.5 GB	3	1
... Loyal Mistral Maid 32K V0.2 A	32K / 21.5 GB	3	1
Chikuma 10.7B V2	32K / 21.4 GB	10	0
PiVoT 10.7B Mistral V0.2 RP	32K / 21.4 GB	67	7
Mark1 Revision 10.7B	32K / 42.9 GB	16	1

Note: green Score (e.g. "73.2") means that the model is better than maywell/PiVoT-10.7B-Mistral-v0.2.